Aruna S

arunasank
·

AI & ML interests

Interpretability, AI & Society, models vs the brain

Recent Activity

updated a model about 6 hours ago
arunasank/gemma2-3-results
published a model about 8 hours ago
arunasank/gemma2-3-results
updated a model 3 days ago
arunasank/sae-scoping-recover
View all activity

Organizations

Massachusetts Institute of Technology's profile picture Mechanistic Interpretability Benchmark's profile picture